{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/guiding-extractive-summarization-with","title":"Guiding Extractive Summarization with Question-Answering Rewards","arxiv_id":"1904.02321","date":"2019-04-04","proceeding":"NAACL 2019 6","authors":["Kristjan Arumae","Fei Liu"],"abstract":"Highlighting while reading is a natural behavior for people to track salient\ncontent of a document. It would be desirable to teach an extractive summarizer\nto do the same. However, a major obstacle to the development of a supervised\nsummarizer is the lack of ground-truth. Manual annotation of extraction units\nis cost-prohibitive, whereas acquiring labels by automatically aligning human\nabstracts and source documents can yield inferior results. In this paper we\ndescribe a novel framework to guide a supervised, extractive summarization\nsystem with question-answering rewards. We argue that quality summaries should\nserve as a document surrogate to answer important questions, and such\nquestion-answer pairs can be conveniently obtained from human abstracts. The\nsystem learns to promote summaries that are informative, fluent, and perform\ncompetitively on question-answering. Our results compare favorably with those\nreported by strong summarization baselines as evaluated by automatic metrics\nand human assessors.","url_abs":"http://arxiv.org/abs/1904.02321v1","url_pdf":"http://arxiv.org/pdf/1904.02321v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"guiding-extractive-summarization-with","repo_url":"https://github.com/ucfnlp/summ_qa_rewards","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.02321","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}